quantumbitcz/forge-history
skills/forge-history/SKILL.md
[read-only] View trends across multiple pipeline runs -- score oscillations, agent effectiveness, common findings, and PREEMPT health. Use when you want to see how quality has changed over time, identify recurring issues, or review past pipeline run outcomes.
testing
Updated Apr 20, 2026
$ install --global
skillsauthnpx skillsauth add quantumbitcz/dev-pipeline forge-historyInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 20, 2026, 5:16 AM4.9s1 file scanned
SKILL.md
- name:
- forge-history
- description:
- [read-only] View trends across multiple pipeline runs -- score oscillations, agent effectiveness, common findings, and PREEMPT health. Use when you want to see how quality has changed over time, identify recurring issues, or review past pipeline run outcomes.
- allowed-tools:
- ['Read', 'Bash', 'Glob', 'Grep']
- disable-model-invocation:
- false
/forge-history -- Pipeline Run History
Flags
- --help: print usage and exit 0
- --json: structured JSON output
Exit codes
See shared/skill-contract.md for the standard exit-code table.
Prerequisites
Before any action, verify:
- Git repository: Run
git rev-parse --show-toplevel 2>/dev/null. If fails: report "Not a git repository. Navigate to a project directory." and STOP. - Forge initialized: Check
.claude/forge.local.mdexists. If not: report "Forge not initialized. Run /forge-init first." and STOP. - History data exists: Check at least one of these sources:
.claude/forge-log.mdwith run entries.forge/reports/with report files If neither exists: report "No pipeline history found. Run/forge-runto start building history." and STOP.
Instructions
1. Gather History Data
Read all available history sources:
- Forge log (
.claude/forge-log.md): Primary source -- contains per-run entries with dates, requirements, scores, verdicts, and retrospective notes. - Run reports (
.forge/reports/): Detailed per-run reports with findings, agent dispatches, and timing data. - Learnings (
shared/learnings/and.forge/learnings/): PREEMPT items and agent effectiveness records.
If forge-log.md is very large (>500 lines), summarize the last 10 runs instead of all runs.
2. Present Quality Score Trend
Extract from forge-log.md each run's date, requirement summary, final quality score, verdict, total fix cycles (verify + review), and wall time:
## Pipeline Run History
### Quality Score Trend
| Date | Requirement | Score | Verdict | Fix Cycles | Duration |
|------|-------------|-------|---------|------------|----------|
Compute trend direction: improving (last 3 scores ascending), declining (descending), or stable (within oscillation tolerance).
3. Present Most Common Findings
Aggregate finding categories across all runs. Show top 5 by frequency:
### Most Common Findings
1. {CATEGORY} ({N} runs) -- {typical description}
2. ...
Identify findings that appear in 3+ runs as convention candidates -- patterns the team consistently triggers that should be codified as project rules.
4. Present Agent Effectiveness
If agent effectiveness data exists in forge-log.md (added by retrospective):
### Agent Effectiveness
| Agent | Runs | Avg Time | Avg Findings | FP Rate |
|---|---|---|---|---|
If no effectiveness data: report "Agent effectiveness tracking not yet available. Will populate after future runs."
5. Present PREEMPT Health
Read learnings files for PREEMPT items:
### PREEMPT Health
- Active items: {count} (HIGH: {n}, MEDIUM: {n}, LOW: {n})
- Archived items: {count}
- Last promotion: {date} -- {item description}
- Decay candidates: {count} items with 10+ unused runs
If no PREEMPT data: report "No PREEMPT items found."
6. Cross-Run Trend Summary
Synthesize the data into actionable observations:
- Score trajectory over the last 5 runs
- Whether convergence is getting faster or slower
- Top recurring finding that should become a convention
Error Handling
| Condition | Action | |-----------|--------| | Prerequisites fail | Report specific error message and STOP | | forge-log.md missing | Fall back to reports directory. If also missing, STOP with guidance | | forge-log.md unparseable | Report "forge-log.md has unexpected format. Showing raw content summary." and display what can be extracted | | Reports directory empty | Work from forge-log.md alone, note limited data | | State corruption | This skill is read-only and does not depend on state.json |
Important
- This is read-only -- do not modify any files
- If forge-log.md is very large (>500 lines), summarize the last 10 runs instead of all runs
- If reports directory does not exist, work from forge-log.md alone
See Also
/forge-status-- Check the current (active) pipeline run state/forge-insights-- Deeper cross-run analytics with cost analysis, convergence patterns, and memory health/forge-profile-- Detailed performance profiling of a single pipeline run/forge-recover diagnose-- Diagnose pipeline health issues when something looks wrong
Related Skills
quantumbitcz/forge
development
VerifiedTrustedCommunity
[writes] Build, fix, deploy, review, or modify code in this project. Universal entry for the forge pipeline. Auto-bootstraps on first run; brainstorms before planning when given a feature description. Use when you want to take any productive action: implementing features, fixing bugs, reviewing branches, deploying, committing, running migrations.
SKILL.mdUpdated Apr 30, 2026
quantumbitcz/forge-admin
tools
VerifiedTrustedCommunity
[writes] Manage forge state and configuration: recovery, abort, config edits, session handoff, automations, playbooks, output compression, knowledge graph maintenance. Use when you need to recover from broken pipeline state, edit settings, or manage long-lived state.
SKILL.mdUpdated Apr 30, 2026
quantumbitcz/forge-handoff
development
VerifiedTrustedCommunity
[writes] Create, list, show, resume, or search forge session handoffs. Use when context is getting heavy and you want to transfer a forge run or conversation into a fresh Claude Code session, or to resume from a prior handoff artefact. Subcommands - no args (write), list, show, resume, search.
SKILL.mdUpdated Apr 23, 2026
quantumbitcz/forge-graph
development
VerifiedTrustedCommunity
[writes] Manage the Neo4j knowledge graph. Subcommands: init, rebuild (writes); status, query <cypher>, debug (read-only). Requires Docker. No default — an explicit subcommand is required. Use when setting up the graph for the first time, rebuilding after major refactors, checking graph health, or running ad-hoc Cypher diagnostics.
SKILL.mdUpdated Apr 21, 2026